Learning Melanocytic Cell Masks from Adjacent Stained Tissue
This work addresses the need for automated and reliable segmentation of melanocytic cells in skin cancer diagnosis, which is incremental as it adapts existing methods to a specific medical imaging challenge.
The paper tackled the problem of low interrater reliability in melanoma diagnosis by developing a deep neural network for melanocytic cell segmentation from H&E stained sections using paired IHC of adjacent tissue sections as ground truth, achieving a mean IOU of 0.64.
Melanoma is one of the most aggressive forms of skin cancer, causing a large proportion of skin cancer deaths. However, melanoma diagnoses by pathologists shows low interrater reliability. As melanoma is a cancer of the melanocyte, there is a clear need to develop a melanocytic cell segmentation tool that is agnostic to pathologist variability and automates pixel-level annotation. Gigapixel-level pathologist labeling, however, is impractical. Herein, we propose a means to train deep neural networks for melanocytic cell segmentation from hematoxylin and eosin (H&E) stained sections and paired immunohistochemistry (IHC) of adjacent tissue sections, achieving a mean IOU of 0.64 despite imperfect ground-truth labels.